MSK SPECTRUM marker positivity fractions
Florian Uhlitz
2021-02-22
library(magrittr)
library(tidyverse)
library(Seurat)
library(readxl)
library(cowplot)
library(colorblindr)
library(viridis)
library(grid)
library(ggpubr)
pcut <- params$pcut## load global vars:
source("_src/global_vars.R")
# meta_tbl
# clrs
# markers_v6
# markers_v6_super
# cell_type_super_lookup## load data
seu_obj_cc <- read_rds("/work/shah/uhlitzf/data/SPECTRUM/freeze/v6/Ovarian.cancer.cell_processed_filtered.rds")
seu_obj_ml <- read_rds("/work/shah/uhlitzf/data/SPECTRUM/freeze/v6/Myeloid.super_processed_filtered_annotated.rds")
seu_obj_fb <- read_rds("/work/shah/uhlitzf/data/SPECTRUM/freeze/v6/Fibroblast.super_processed_filtered_annotated.rds")
gois <- c(grep("^ALDH", rownames(seu_obj_cc), value = T),
"PROM1", "CD68", "PECAM1", "NT5E") %>% .[!str_detect(. ,"-AS")]
myfeatures <- c("sample", "umapharmony_1", "umapharmony_2", "cell_type", "cluster_label")
get_data_wrapper <- . %>%
FetchData(c(myfeatures, gois)) %>%
as_tibble() %>%
gather(gene, value, -c(1:length(myfeatures))) %>%
left_join(meta_tbl, by = "sample")
plot_data <- bind_rows(
`Ovarian.cancer.cell` = get_data_wrapper(seu_obj_cc),
`Fibroblast` = get_data_wrapper(seu_obj_fb),
`Myeloid.cell` = get_data_wrapper(seu_obj_ml),
.id = "cell_type_super"
)
plot_data_full <- plot_data
plot_data_sub <- sample_n(plot_data, 100000)
plot_data <- plot_data_sub
write_tsv(plot_data_sub, "cache.tsv")
plot_data <- read_tsv("cache.tsv")
plot_data <- plot_data_full1 Overview
1.1 considered data
We assess marker gene expression in a HGSOC cohort of 42 patients across major cell types:
- Fibroblasts: 154k
- Myeloid cells: 162k
- Cancer cells: 214k
Marker genes:
cat(gois, sep = ", ")## ALDH4A1, ALDH9A1, ALDH1L1, ALDH7A1, ALDH5A1, ALDH8A1, ALDH1B1, ALDH1A1, ALDH3B2, ALDH3B1, ALDH18A1, ALDH1L2, ALDH2, ALDH6A1, ALDH1A2, ALDH1A3, ALDH3A2, ALDH3A1, ALDH16A1, PROM1, CD68, PECAM1, NT5E1.2 Marker percentage
plot_data_comp <- plot_data %>%
mutate(expressed = value > 0) %>%
group_by(patient_id_short, cell_type_super, gene) %>%
summarise(pct.expressed = sum(expressed)/length(expressed))
write_tsv(plot_data_comp, "mehta_marker_expression_pct.tsv")
ggplot(plot_data_comp) +
geom_boxplot(aes(gene, pct.expressed)) +
facet_grid(~cell_type_super) +
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0))
2 Detailed single cell marker expression data
cluster_label_clrs <- c(clrs$cluster_label$Fibroblast.super,
clrs$cluster_label$Myeloid.super,
clrs$cluster_label$Ovarian.cancer.super)
plot_data <- plot_data %>%
mutate(cluster_label = ordered(cluster_label, levels = names(cluster_label_clrs)))
common_layers <- list(
remove_xaxis,
remove_yaxis
)
ggplot(distinct(plot_data, umapharmony_1, umapharmony_2, cell_type_super, .keep_all = T)) +
geom_point(aes(umapharmony_1, umapharmony_2,
color = cluster_label), size = 0.01, alpha = 0.2) +
facet_grid(~cell_type_super) +
scale_color_manual(values = cluster_label_clrs) +
guides(color = guide_legend(override.aes = list(size = 3, alpha = 1))) +
common_layers
2.1 in the embedding
ggplot() +
geom_point(aes(umapharmony_1, umapharmony_2),
size = 0.01, alpha = 0.2, color = "grey80",
data = filter(plot_data, value == 0)) +
geom_point(aes(umapharmony_1, umapharmony_2,
color = value), size = 0.01, alpha = 0.2,
data = filter(plot_data, value > 0)) +
facet_grid(gene~cell_type_super) +
scale_color_viridis() +
common_layers
2.2 box plot distributions wrt cell type subclusters
ggplot(plot_data) +
geom_boxplot(aes(cluster_label, value, fill = cluster_label)) +
facet_grid(gene~cell_type_super, space = "free", scales = "free") +
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0)) +
guides(fill = F) +
scale_fill_manual(values = cluster_label_clrs)
3 session info
devtools::session_info()## ─ Session info ───────────────────────────────────────────────────────────────
## setting value
## version R version 3.6.2 (2019-12-12)
## os Debian GNU/Linux 10 (buster)
## system x86_64, linux-gnu
## ui X11
## language (EN)
## collate en_US.UTF-8
## ctype en_US.UTF-8
## tz Etc/UTC
## date 2021-02-22
##
## ─ Packages ───────────────────────────────────────────────────────────────────
## package * version date lib
## abind 1.4-5 2016-07-21 [2]
## ape 5.3 2019-03-17 [2]
## assertthat 0.2.1 2019-03-21 [2]
## backports 1.1.10 2020-09-15 [1]
## bibtex 0.4.2.2 2020-01-02 [2]
## Biobase 2.46.0 2019-10-29 [2]
## BiocGenerics 0.32.0 2019-10-29 [2]
## bitops 1.0-6 2013-08-17 [2]
## broom 0.7.2 2020-10-20 [1]
## callr 3.4.2 2020-02-12 [1]
## car 3.0-8 2020-05-21 [1]
## carData 3.0-4 2020-05-22 [1]
## caTools 1.17.1.4 2020-01-13 [2]
## cellranger 1.1.0 2016-07-27 [2]
## cli 2.0.2 2020-02-28 [1]
## cluster 2.1.0 2019-06-19 [3]
## codetools 0.2-16 2018-12-24 [3]
## colorblindr * 0.1.0 2020-01-13 [2]
## colorspace * 1.4-2 2019-12-29 [2]
## cowplot * 1.0.0 2019-07-11 [2]
## crayon 1.3.4 2017-09-16 [1]
## curl 4.3 2019-12-02 [2]
## data.table 1.12.8 2019-12-09 [2]
## DBI 1.1.0 2019-12-15 [2]
## dbplyr 2.0.0 2020-11-03 [1]
## desc 1.2.0 2018-05-01 [2]
## devtools 2.2.1 2019-09-24 [2]
## digest 0.6.25 2020-02-23 [1]
## dplyr * 1.0.2 2020-08-18 [1]
## ellipsis 0.3.1 2020-05-15 [1]
## evaluate 0.14 2019-05-28 [2]
## fansi 0.4.1 2020-01-08 [2]
## farver 2.0.3 2020-01-16 [1]
## fitdistrplus 1.0-14 2019-01-23 [2]
## forcats * 0.5.0 2020-03-01 [1]
## foreign 0.8-74 2019-12-26 [3]
## fs 1.5.0 2020-07-31 [1]
## future 1.15.1 2019-11-25 [2]
## future.apply 1.4.0 2020-01-07 [2]
## gbRd 0.4-11 2012-10-01 [2]
## gdata 2.18.0 2017-06-06 [2]
## generics 0.0.2 2018-11-29 [2]
## ggplot2 * 3.3.2 2020-06-19 [1]
## ggpubr * 0.4.0 2020-06-27 [1]
## ggrepel 0.8.1 2019-05-07 [2]
## ggridges 0.5.2 2020-01-12 [2]
## ggsignif 0.6.0 2019-08-08 [1]
## globals 0.12.5 2019-12-07 [2]
## glue 1.3.2 2020-03-12 [1]
## gplots 3.0.1.2 2020-01-11 [2]
## gridExtra 2.3 2017-09-09 [2]
## gtable 0.3.0 2019-03-25 [2]
## gtools 3.8.1 2018-06-26 [2]
## haven 2.3.1 2020-06-01 [1]
## hms 0.5.3 2020-01-08 [1]
## htmltools 0.5.1.1 2021-01-22 [1]
## htmlwidgets 1.5.1 2019-10-08 [2]
## httr 1.4.2 2020-07-20 [1]
## ica 1.0-2 2018-05-24 [2]
## igraph 1.2.5 2020-03-19 [1]
## irlba 2.3.3 2019-02-05 [2]
## jsonlite 1.7.1 2020-09-07 [1]
## KernSmooth 2.23-16 2019-10-15 [3]
## knitr 1.26 2019-11-12 [2]
## labeling 0.3 2014-08-23 [2]
## lattice 0.20-38 2018-11-04 [3]
## lazyeval 0.2.2 2019-03-15 [2]
## leiden 0.3.1 2019-07-23 [2]
## lifecycle 0.2.0 2020-03-06 [1]
## listenv 0.8.0 2019-12-05 [2]
## lmtest 0.9-37 2019-04-30 [2]
## lsei 1.2-0 2017-10-23 [2]
## lubridate 1.7.9.2 2020-11-13 [1]
## magrittr * 2.0.1 2020-11-17 [1]
## MASS 7.3-51.5 2019-12-20 [3]
## Matrix 1.2-18 2019-11-27 [3]
## memoise 1.1.0 2017-04-21 [2]
## metap 1.2 2019-12-08 [2]
## mnormt 1.5-5 2016-10-15 [2]
## modelr 0.1.8 2020-05-19 [1]
## multcomp 1.4-12 2020-01-10 [2]
## multtest 2.42.0 2019-10-29 [2]
## munsell 0.5.0 2018-06-12 [2]
## mutoss 0.1-12 2017-12-04 [2]
## mvtnorm 1.0-12 2020-01-09 [2]
## nlme 3.1-143 2019-12-10 [3]
## npsurv 0.4-0 2017-10-14 [2]
## numDeriv 2016.8-1.1 2019-06-06 [2]
## openxlsx 4.1.5 2020-05-06 [1]
## pbapply 1.4-2 2019-08-31 [2]
## pillar 1.4.6 2020-07-10 [1]
## pkgbuild 1.0.6 2019-10-09 [2]
## pkgconfig 2.0.3 2019-09-22 [1]
## pkgload 1.0.2 2018-10-29 [2]
## plotly 4.9.1 2019-11-07 [2]
## plotrix 3.7-7 2019-12-05 [2]
## plyr 1.8.5 2019-12-10 [2]
## png 0.1-7 2013-12-03 [2]
## prettyunits 1.1.1 2020-01-24 [1]
## processx 3.4.2 2020-02-09 [1]
## ps 1.3.2 2020-02-13 [1]
## purrr * 0.3.4 2020-04-17 [1]
## R.methodsS3 1.7.1 2016-02-16 [2]
## R.oo 1.23.0 2019-11-03 [2]
## R.utils 2.9.2 2019-12-08 [2]
## R6 2.4.1 2019-11-12 [1]
## RANN 2.6.1 2019-01-08 [2]
## rappdirs 0.3.1 2016-03-28 [2]
## RColorBrewer 1.1-2 2014-12-07 [2]
## Rcpp 1.0.4 2020-03-17 [1]
## RcppAnnoy 0.0.16 2020-03-08 [1]
## RcppParallel 4.4.4 2019-09-27 [2]
## Rdpack 0.11-1 2019-12-14 [2]
## readr * 1.4.0 2020-10-05 [1]
## readxl * 1.3.1 2019-03-13 [2]
## remotes 2.1.0 2019-06-24 [2]
## reprex 0.3.0 2019-05-16 [2]
## reshape2 1.4.3 2017-12-11 [2]
## reticulate 1.14 2019-12-17 [2]
## rio 0.5.16 2018-11-26 [1]
## rlang 0.4.8 2020-10-08 [1]
## rmarkdown 2.0 2019-12-12 [2]
## ROCR 1.0-7 2015-03-26 [2]
## rprojroot 1.3-2 2018-01-03 [2]
## rstatix 0.6.0 2020-06-18 [1]
## rstudioapi 0.11 2020-02-07 [1]
## rsvd 1.0.3 2020-02-17 [1]
## Rtsne 0.15 2018-11-10 [2]
## rvest 0.3.6 2020-07-25 [1]
## sandwich 2.5-1 2019-04-06 [2]
## scales 1.1.0 2019-11-18 [2]
## sctransform 0.2.1 2019-12-17 [2]
## SDMTools 1.1-221.2 2019-11-30 [2]
## sessioninfo 1.1.1 2018-11-05 [2]
## Seurat * 3.1.2 2019-12-12 [2]
## sn 1.5-4 2019-05-14 [2]
## stringi 1.5.3 2020-09-09 [1]
## stringr * 1.4.0 2019-02-10 [1]
## survival 3.1-8 2019-12-03 [3]
## testthat 2.3.2 2020-03-02 [1]
## TFisher 0.2.0 2018-03-21 [2]
## TH.data 1.0-10 2019-01-21 [2]
## tibble * 3.0.4 2020-10-12 [1]
## tidyr * 1.1.2 2020-08-27 [1]
## tidyselect 1.1.0 2020-05-11 [1]
## tidyverse * 1.3.0 2019-11-21 [2]
## tsne 0.1-3 2016-07-15 [2]
## usethis 1.5.1 2019-07-04 [2]
## uwot 0.1.5 2019-12-04 [2]
## vctrs 0.3.5 2020-11-17 [1]
## viridis * 0.5.1 2018-03-29 [2]
## viridisLite * 0.3.0 2018-02-01 [2]
## withr 2.3.0 2020-09-22 [1]
## xfun 0.12 2020-01-13 [2]
## xml2 1.3.2 2020-04-23 [1]
## yaml 2.2.1 2020-02-01 [1]
## zip 2.0.4 2019-09-01 [1]
## zoo 1.8-7 2020-01-10 [2]
## source
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.3)
## CRAN (R 3.6.2)
## Bioconductor
## Bioconductor
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## Github (clauswilke/colorblindr@1ac3d4d)
## R-Forge (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.3)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.3)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.3)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.3)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## Bioconductor
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.3)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.3)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.3)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.3)
## CRAN (R 3.6.3)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.3)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
## CRAN (R 3.6.2)
##
## [1] /home/uhlitzf/R/lib
## [2] /usr/local/lib/R/site-library
## [3] /usr/local/lib/R/library